Li-ion batteries have become the most important technology for electric mobility. One of the most pressing challenges is the development of reliable methods for battery state-of-health (SOH) diagnosis and estimation of remaining useful life. In electric mobility scenario, battery capacity degradation prediction is crucial to ensure service availability and life duration. This research work provides a comprehensive comparative analysis of neural networks for a data-driven approach suitable for SOH estimation on single cells, stressed under laboratory conditions. For this purpose, different neural networks (i.e., LSTM, GRU, 1D-CNN, CNN-LSTM) are trained and optimized on NASA Randomized Battery Usage dataset. Experimental results demonstrate that data-driven neural networks generally performed well SOH estimation on single cells. In detail, the 1D-CNN best predicts SOH and has the lowest variance in the output. The LSTM have the highest variance in estimating SOH, while GRU and CNN-LSTM tend to overestimate and underestimate the value of SOH, respectively.

Comparative Analysis of Neural Networks Techniques for Lithium-ion Battery SOH Estimation / Aliberti, Alessandro; Boni, Filippo; Perol, Alessandro; Zampolli, Marco; Jaboeuf, Remi Jacques Philibert; Tosco, Paolo; Macii, Enrico; Patti, Edoardo. - (2022), pp. 1355-1361. (Intervento presentato al convegno 46th IEEE Annual Computers, Software, and Applications Conference (COMPSAC 2022) tenutosi a Virtual Conference (due to Covid-19) nel 27 June 2022 - 01 July 2022) [10.1109/COMPSAC54236.2022.00214].

Comparative Analysis of Neural Networks Techniques for Lithium-ion Battery SOH Estimation

Aliberti, Alessandro;Macii, Enrico;Patti, Edoardo
2022

Abstract

Li-ion batteries have become the most important technology for electric mobility. One of the most pressing challenges is the development of reliable methods for battery state-of-health (SOH) diagnosis and estimation of remaining useful life. In electric mobility scenario, battery capacity degradation prediction is crucial to ensure service availability and life duration. This research work provides a comprehensive comparative analysis of neural networks for a data-driven approach suitable for SOH estimation on single cells, stressed under laboratory conditions. For this purpose, different neural networks (i.e., LSTM, GRU, 1D-CNN, CNN-LSTM) are trained and optimized on NASA Randomized Battery Usage dataset. Experimental results demonstrate that data-driven neural networks generally performed well SOH estimation on single cells. In detail, the 1D-CNN best predicts SOH and has the lowest variance in the output. The LSTM have the highest variance in estimating SOH, while GRU and CNN-LSTM tend to overestimate and underestimate the value of SOH, respectively.
2022
978-1-6654-8810-5
File in questo prodotto:
File Dimensione Formato  
2022___Compsac2022___Boni.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 1.1 MB
Formato Adobe PDF
1.1 MB Adobe PDF Visualizza/Apri
Comparative_Analysis_of_Neural_Networks_Techniques_for_Lithium-ion_Battery_SOH_Estimation.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 460.1 kB
Formato Adobe PDF
460.1 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2970693